Semantic feature mining is essential to semantic-based image retrieval technique.
Here, we choose sigmoid function as the activation function of the layers for spectral feature mining.
Therefore, in this article, a novel approach is proposed to achieve region-level semantic feature mining.
Therefore, DNN can be used for fault feature mining and intelligent fault diagnosis.
However, most of the existing high-level semantic feature mining methods are based on pixel-level features.
In this paper, we introduced a novel feature mining algorithm, contextual deep learning, which is especially effective for HSI classification.
In this work, we present an effective way to combine unsupervised feature learning with discriminative feature mining.
Data mining techniques, including text mining, linguistic feature mining, and classification by text features, can be used to analyze the "caller side" of the transcripts of these calls.
The process of semantic feature mining can be divided into two steps: low-level feature extraction and high-level semantic feature extraction.
Because the reliability of feature for every pixel determines the accuracy of classification, it is important to design a specialized feature mining algorithm for hyperspectral image classification.
